INTERNATIONAL CONFERENCE RECENT ADVANCES

IN NATURAL LANGUAGE PROCESSING

R A N L P 2 0 1 9

Natural Language Processing in a Deep Learning World

P R O C E E D I N G S

Edited by Galia Angelova, Ruslan Mitkov, Ivelina Nikolova, Irina Temnikova

Varna, Bulgaria 2–4 September, 2019

ii

INTERNATIONAL CONFERENCE RECENT ADVANCES IN

NATURAL LANGUAGE PROCESSING 2019

Natural Language Processing in a Deep Learning World

PROCEEDINGS2 volumes

Varna, Bulgaria 2–8 September 2019

Print ISBN 978-954-452-055-7 Online ISBN 978-954-452-056-4 Series Print

ISSN 1313-8502 Series Online ISSN 2603-2813

Designed and Printed by INCOMA Ltd. Shoumen, BULGARIA

iii

Preface

Welcome to the 12th International Conference on “Recent Advances in Natural Language Processing” (RANLP 2019) in Varna, Bulgaria, 2-4 September 2019. The main objective of the conference is to give researchers the opportunity to present new results in Natural Language Processing (NLP) based on modern theories and methodologies.

The Conference is preceded by the First Summer school on Deep Learning in NLP (29-30 August 2019) and two days of tutorials (31 August – 1 September 2019).

The Summer School lectures are given by Kyunghyun Cho (New York University), Marek Rei (University of Cambridge), Tim Rocktäschel (University College London) and Hinrich Schütze (Ludwig Maximilian University, Munich). Training in practical sessions is provided by Heike Adel (Stuttgart University), Alexander Popov (Institute of Information and Communication Technologies, Bulgarian Academy of Sciences), Omid Rohanian and Shiva Taslimipoor (University of Wolverhampton).

Tutorials are given by the following lecturers: Antonio Miceli Barone (University of Edinburgh) and Sheila Castilho (Dublin City University), Valia Kordoni (Humboldt University, Berlin), Preslav Nakov (Qatar Computing Research Institute, HBKU), Vlad Niculae and Tsvetomila Mihaylova (Institute of Telecommunications, Lisbon).

The conference keynote speakers are: • Kyunghyun Cho (New York University),• Ken Church (Baidu),• Preslav Nakov (Qatar Computing Research Institute, HBKU),• Sebastian Padó (Stuttgart University),• Hinrich Schütze (Ludwig Maximilian University, Munich).

This year 18 regular papers, 37 short papers, 95 posters, and 7 demos have been accepted for presentation at the conference. The selection rate of accepted papers is: regular papers 8,7%, short papers 26,7%, posters and demo papers – 72%.

The proceedings cover a wide variety of NLP topics, including but not limited to: deep learning; machine translation; opinion mining and sentiment analysis; semantics and discourse; named entity recognition; coreference resolution; corpus annotation; parsing and morphology; text summarisation and simplification; event extraction; fact checking and rumour analysis; NLP for healthcare; and NLP for social media.

In 2019 RANLP hosts four post-conference workshops on influential NLP topics: the 2nd Workshop on Human-Informed Translation and Interpreting Тechnology (HiT-IT 2019), the

iv

12th Workshop on Building and Using Comparable Corpora (BUCC), the Multiling 2019 Workshop: Summarization Across Languages, Genres аnd Sources as well as an Workshop on Language Technology for Digital Historical Archives with a Special Focus on Central-, (South-)Eastern Europe, Middle East and North Africa. The International Conference Biographical Data in a Digital World 2019 is another event held on 5-6 September 2019 in parallel with the RANLP post-conference Workshops.

We would like to thank all members of the Programme Committee and all additional reviewers. Together they have ensured that the best papers were included in the Proceedings and have provided invaluable comments for the authors.

Finally, special thanks go to the University of Wolverhampton, the Institute of Information and Communication Technologies at the Bulgarian Academy of Sciences, the Bulgarian National Science Fund, Ontotext and IRIS.AI for their generous support of RANLP.

Welcome to Varna and we hope that you enjoy the conference!

The RANLP 2019 Organisers

v

The International Conference RANLP–2019 is organised by:

Research Group in Computational Linguistics, University of Wolverhampton, UK

Linguistic Modelling and Knowledge Processing Department, Institute of Information and Communication Technologies, Bulgarian Academy of Sciences, Bulgaria

RANLP–2019 is partially supported by:

National Science Fund, Ministry of Education and Science, Bulgaria

Ontotext AD

IRIS.AI

Programme Committee Chair:

Ruslan Mitkov, University of Wolverhampton, UK

Organising Committee Chair:

Galia Angelova, Bulgarian Academy of Sciences, Bulgaria

Workshop Coordinator:

Kiril Simov, Bulgarian Academy of Sciences, Bulgaria

Tutorial Coordinator:

Preslav Nakov, Qatar Computing Research Institute, HBKU, Qatar

Proceedings Printing:

Nikolai Nikolov, INCOMA Ltd., Shoumen, Bulgaria

Programme Committee Coordinators:

Ivelina Nikolova, Bulgarian Academy of Sciences Irina Temnikova, Bulgarian Academy of Sciences

Programme Committee:

Ahmed Abdelali (Hamad Bin Khalifa University, Qatar)Cengiz Acarturk (Middle East Technical University, Turkey)Guadalupe Aguado-de-Cea (Polytechnic University of Madrid, Spain)Luis Alfonso Urena Lopez (University of Jaen, Spain)Hassina Aliane (Research Center on Scientific and Technical Information, Algeria)Pascal Amsili (University of Paris Diderot, France)Galia Angelova (Bulgarian Academy of Sciences, Bulgaria)Riza Batista-Navarro (University of Manchester, United Kingdom)Kalina Bontcheva (University of Sheffield, United Kingdom)Svetla Boytcheva (Bulgarian Academy of Sciences, Bulgaria)Antonio Branco (University of Lisbon, Portugal)Chris Brew (Digital Operatives)Nicoletta Calzolari (Italian National Research Council, Italy)Sheila Castilho (Dublin City University, Ireland)Key-Sun Choi (Korea Advanced Institute of Science and Technology, South Korea)Kenneth Church (Baidu, United States of America)Kevin Cohen (University of Colorado School of Medicine, United States of America)Gloria Corpas Pastor (University of Malaga, Spain)Dan Cristea (University of Las, i, Romania)Antonio Ferrandez Rodrıguez (University of Alicante, Spain)Fumiyo Fukumoto (University of Yamanashi, Japan)Proszeky Gabor (Pazmany Peter Catholic University & Bionics, Hungary)Alexander Gelbukh (National Polytechnic Institute, Mexico)Yota Georgakopoulou (Athena Consultancy, Greece)Ralph Grishman (New York University, United States of America)Veronique Hoste (Ghent University, Belgium)Diana Inkpen (University of Ottawa, Canada)Hitoshi Isahara (Toyohashi University of Technology, Japan)Milos Jakubıcek (Lexical Computing Ltd)Alma Kharrat (Microsoft)Udo Kruschwitz (University of Essex, United Kingdom)Sandra Kubler (Indiana University, United States of America)Katia Lida Kermanidis (Ionian University, Greece)Natalia Loukachevitch (Lomonosov Moscow State University, Russia)Eid Mohamed (Doha Institute for Graduate Studies, Qatar)Emad Mohamed (University of Wolverhampton, United Kingdom)Johanna Monti (University of Naples L’Orientale, Italy)Andres Montoyo (University of Alicante, Spain)Alessandro Moschitti (Amazon)Rafael Munoz Guillena (University of Alicante, Spain)Preslav Nakov (Qatar Computing Research Institute, Qatar)Roberto Navigli (Sapienza University of Rome, Italy)Raheel Nawaz (Manchester Metropolitan University, United Kingdom)Mark-Jan Nederhof (University of St Andrews, United Kingdom)Ivelina Nikolova (Bulgarian Academy of Sciences, Bulgaria)Kemal Oflazer (Carnegie Mellon University, Qatar)Maciej Ogrodniczuk (Polish Academy of Sciences, Poland)

vi

Constantin Orasan (University of Wolverhampton, United Kingdom)Petya Osenova (Sofia University and Bulgarian Academy of Sciences, Bulgaria) Sebastian Pado (Stuttgart University, Germany)Noa P. Cruz Diaz (Artificial Intelligence Excellence Center, Bankia, Spain)Liviu P. Dinu (University of Bucharest, Romania)Pavel Pecina (Charles University, Czech Republic)Stelios Piperidis (Athena Research Center, Greece)Massimo Poesio (University of Essex, United Kingdom)Horacio Rodrıguez (Polytechnic University of Catalonia, Spain)Paolo Rosso (Polytechnic University of Valencia, Spain)Vasile Rus (The University of Memphis, United States of America)Frederique Segond (Viseo)Kiril Simov (Bulgarian Academy of Sciences, Bulgaria)Vilelmini Sosoni (Ionian University, Greece)Keh-Yih Su (Institute of Information Science, Academia Sinica, Taiwan)Stan Szpakowicz (University of Ottawa, Canada)Hristo Tanev (European Commission, Belgium)Shiva Taslimipoor (University of Wolverhampton, United Kingdom)Irina Temnikova (Sofia University, Bulgaria)Dan Tufis, (Romanian Academy of Sciences, Romania)Aline Villavicencio (University of Essex, United Kingdomand Federal University of Rio Grande do Sul, Brazil)Yorick Wilks (Florida Institute for Human and Machine Cognition,United States of America )Mai Zaki (American University of Sharjah, United Arab Emirates)Marcos Zampieri (University of Wolverhampton, United Kingdom)Michael Zock (University of Aix-Marseille, France)

Reviewers:

Ahmed AbuRa’ed (University Pompeu Fabra, Spain)Mattia A. Di Gangi (University of Trento, Italy)Itziar Aldabe (University of Paıs Vasco, Spain)Ahmed Ali (Hamad Bin Khalifa University, Qatar)Ahmed Amine Aliane (Research Center on Scientific and Technical Information, Algeria)Le An Ha (University of Wolverhampton, United Kingdom)Atefeh (Anna) Farzindar (University of Southern California, United States of America) Joao Antonio Rodrigues (University of Lisboa, Portugal)Pepa Atanasova (University of Copenhagen, Denmark)Mohammed Attia (George Washington University, United States of America)Parnia Bahar (Aachen University, Germany)Belahcene Bahloul (University of Khemis Miliana, Algeria)Eduard Barbu (University of Tartu, Estonia)Alberto Barron-Cedeno (University of Bologna, Italy)Leonor Becerra (Jean Monnet University, France)Andrea Bellandi (National Research Council, Italy)Fernando Benites (ZHAW School of Engineering, Switzerland)Victoria Bobicev (Technical University of Moldova, Moldova)

vii

Antonina Bondarenko (Lipetsk State Technical University, Russia)Aurelien Bossard (University Paris 8, France)Aljoscha Burchardt (German Research Centre for Artificial Intelligence, Germany) Lindsay Bywood (University of Westminster, United Kingdom)Ruket Cakici (Middle East Technical University, Turkey)Iacer Calixto (University of Amsterdam, Netherlands and New York University,United States of America)Pablo Calleja (Polytechnic University of Madrid, Spain)Erik Cambria (Nanyang Technological University, Singapore)Kai Cao (New York University, United States of America)Thiago Castro Ferreira (Tilburg University, Netherlands)Yue Chen (Queen Mary University of London, United Kingdom)Mihaela Colhon (University of Craiova, Romania)Daniel Dakota (Indiana University, United States of America)Kareem Darwish (Hamad Bin Khalifa University, Qatar)Orphee De Clercq (Ghent University, Belgium)Kevin Deturck (Viseo)Asma Djaidri (University of Science and Technology Houari Boumediene, Algeria) Mazen Elagamy (Staffordshire University, United Kingdom)Can Erten (University of York, United Kingdom)Luis Espinosa Anke (Cardiff University, United Kingdom)Kilian Evang (University of Dusseldorf, Germany)Richard Evans (University of Wolverhampton, United Kingdom)Stefan Evert (Friedrich–Alexander University, Germany)Anna Feherova (University of Wolverhampton, United Kingdom)Mariano Felice (University of Cambridge, United Kingdom)Corina Forascu (The Alexandru Ioan Cuza University, Romania)Vasiliki Foufi (University of Geneva, Switzerland)Thomas Francois (Universite catholique de Louvain, Belgium)Adam Funk (University of Sheffield, United Kingdom)Bjorn Gamback (Norwegian University of Science and Technology, Norway)Aina Garı Soler (The Computer Science Laboratory for Mechanicsand Engineering Sci-ences, France)Federico Gaspari (Dublin City University, Ireland)Jose G. C. de Souza (eBay)Goran Glavas (University of Mannheim, Germany)Darina Gold (University of Duisburg-Essen, Germany)Reshmi Gopalakrishna Pillai (University of Wolverhampton, United Kingdom)Rohit Gupta (University of Wolverhampton, United Kingdom)Amir Hazem (Nantes University, France)Tomas Hercig (University of West Bohemia, Czech Republic)Yasser Hifny (University of Helwan, Egypt)Diliara Iakubova (Kazan Federal University, Russia)Adrian Iftene (The Alexandru Ioan Cuza University, Romania)Camelia Ignat (European Commission, Belgium)Dmitry Ilvovsky (National Research University Higher School of Economics, Russia) Milos Jakubıcek (Masaryk University, Czech Republic)Arkadiusz Janz (Wroclaw University of Science and Technology, Poland)

viii

Hector Jimenez-Salazar (The Metropolitan Autonomous University, Mexico) Olga Kanishcheva (National Technical University, Ukraine)Georgi Karadzhov (Sofia University, Bulgaria)David Kauchak (Pomona College, United States of America)Yasen Kiprov (Sofia University, Bulgaria)Jan Kocon (Wroclaw University of Science and Technology, Poland) Sarah Kohail (Hamburg University, Germany)Yannis Korkontzelos (Edge Hill University, United Kingdom)Venelin Kovatchev (University of Barcelona, Spain)Peter Krejzl (University of West Bohemia, Czech Republic)Sudip Kumar Naskar (Jadavpur University, India)Maria Kunilovskaya (University of Tyumen, Russia)Andrey Kutuzov (University of Oslo, Norway)Sobha Lalitha Devi (Anna University, India)Gabriella Lapesa (Universitat Stuttgart, Institut fur Maschinelle Sprachverarbeitung, Germany)Todor Lazarov (Bulgarian Academy of Sciences, Bulgaria)Els Lefever (Ghent University, Belgium)Ladislav Lenc (University of West Bohemia, Czech Republic)Elena Lloret (University of Alicante)Pintu Lohar (Dublin City University, Ireland)Epida Loupaki (Aristotle University of Thessaloniki, Greece)Lieve Macken (Ghent University, Belgium)Mireille Makary (University of Wolverhampton, United Kingdom)Michał Marcinczuk (Wroclaw University of Technology, Poland)Angelo Mario Del Grosso (National Research Council of Italy, Italy) Federico Martelli (Babelscape, Italy)Patricia Martin Chozas (Polytechnic University of Madrid, Spain)Eugenio Martınez-Camara (University of Granada, Spain)Irina Matveeva (NexLP, Unites States of America)Flor Miriam Plaza del Arco (University of Jaen, Spain)Arturo Montejo-Raez (University of Jaen, Spain)Paloma Moreda Pozo (University of Alicante, Spain)Diego Moussallem (University of Paderborn, Germany)Sara Moze (University of Wolverhampton, United Kingdom)Nona Naderi (University of Toronto, Canada)Marcin Oleksy (Wrocław University of Science and Technology, Poland) Antoni Oliver (The Open University of Catalonia, Spain)Mihaela Onofrei (University of Iasi, Romania)Arzucan Özgür (Bogazici University, Turkey)Santanu Pal (Saarland University, Germany)Alexander Panchenko (University of Hamburg, Germany)Sean Papay (University of Stuttgart, Germany)Ljudmila Petkovic (University of Belgrade, Serbia)Maciej Piasecki (Wroclaw University of Science and Technology, Poland) Paul Piwek (The Open University, United Kingdom)Alistair Plum (University of Wolverhampton, United Kingdom)Alberto Poncelas (Dublin City University, Ireland)

ix

Alexander Popov (Bulgarian Academy of Sciences, Bulgaria)Maja Popovic ( Dublin City University, Ireland)Dan Povey (Johns Hopkins University, United States of America)Ondrej Prazak (University of West Bohemia, Czech Republic)Prokopis Prokopidis (Research and Innovation Center in Information, Greece)Tharindu Ranasinghe (University of Wolverhampton, United Kingdom)Natalia Resende (Dublin City University, Ireland)Pattabhi RK Rao (Anna University, India)Omid Rohanian (University of Wolverhampton, United Kingdom)Josef Ruppenhofer (Institute for the German Language, Germany)Pavel Rychly (Masaryk University, Czech Republic)Magdalena Rysova (Charles University, Czech Republic)Branislava Sandrih (Belgrade University, Serbia)Estela Saquete (University of Alicante, Spain)Leah Schaede (Indiana University, United States)Ineke Schuurman (University of Leuven, Belgium)Olga Seminck (Paris Diderot University, France)Nasredine Semmar (Laboratory for Integration of Systems and Technology, France)Matthew Shardlow (Manchester Metropolitan University, United Kingdom)Artem Shelmanov (Russian Academy of Sciences, Russia)Dimitar Shterionov (Dublin City University, Ireland)Jennifer Sikos (University of Stuttgart, Germany)Joao Silva (University of Lisboa, Portugal)Vasiliki Simaki (Lancaster University, United Kingdom)Sunayana Sitaram (Microsoft Research, India)Mihailo Skoric (Researcher, Serbia)Felix Stahlberg (University of Cambridge, Department of Engineering, United Kingdom)Kenneth Steimel (Indiana University, United States)Sebastian Stuker (Karlsruhe Institute of Technology, Germany)Yoshimi Suzuki (Shizuoka University, Japan)Liling Tan (Nanyang Technological University, Singapore)Segun Taofeek Aroyehun (National Polytechnic Institute, Mexico )Laura Tolos, i (Self employed data scientist)Elena Tutubalina (Kazan Federal University, Russia)Eleni Tziafa (National and Kapodistrian Unversity of Athens, Greece)Antonio Valerio Miceli Barone (University of Edinburgh, United Kingdom)Mihaela Vela (Saarland University, Germany)Cristina Vertan (University of Hamburg, Germany)Manuel Vilares Ferro (University of Vigo, Spain)Veronika Vincze (University of Szeged, Hungary)Pidong Wang (National University of Singapore, Singapore)Michael Wiegand (Heidelberg University, Germany)Victoria Yaneva (University of Wolverhampton, United Kingdom)Kristina Yordanova (University of Rostock, Germany)Juntao Yu (Queen Mary University of London, United Kingdom)Wajdi Zaghouani (Hamad Bin Khalifa University, Qatar)Kalliopi Zervanou (Eindhoven University of Technology, Netherlands)Ines Zribi (University of Sfax, Tunisia)

x

Table of Contents

Table Structure Recognition Based on Cell Relationship, a Bottom-Up ApproachDarshan Adiga, Shabir Ahmad Bhat, Muzaffar Bashir Shah and Viveka Vyeth . . . . . . . . . . . . . . . . . 1

Identification of Good and Bad News on TwitterPiush Aggarwal and Ahmet Aker . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9

Bilingual Low-Resource Neural Machine Translation with Round-Tripping: The Case of Persian-SpanishBenyamin Ahmadnia and Bonnie Dorr . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18

Enhancing Phrase-Based Statistical Machine Translation by Learning Phrase Representations UsingLong Short-Term Memory Network

Benyamin Ahmadnia and Bonnie Dorr . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25

Automatic Propbank Generation for TurkishKoray Ak and Olcay Taner Yıldız . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33

Multilingual Sentence-Level Bias Detection in WikipediaDesislava Aleksandrova, François Lareau and Pierre André Ménard . . . . . . . . . . . . . . . . . . . . . . . . . . 42

Supervised Morphological Segmentation Using Rich Annotated LexiconEbrahim Ansari, Zdenek Žabokrtský, Mohammad Mahmoudi, Hamid Haghdoost andJonáš Vidra . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 52

Combining Lexical Substitutes in Neural Word Sense InductionNikolay Arefyev, Boris Sheludko and Alexander Panchenko . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 62

Detecting Clitics Related Orthographic Errors in TurkishUgurcan Arıkan, Onur Güngör and Suzan Uskudarli . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 71

Benchmark Dataset for Propaganda Detection in Czech Newspaper TextsVít Baisa, Ondrej Herman and Ales Horak . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 77

Diachronic Analysis of Entities by Exploiting Wikipedia Page RevisionsPierpaolo Basile, Annalina Caputo, Seamus Lawless and Giovanni Semeraro . . . . . . . . . . . . . . . . . 84

Using a Lexical Semantic Network for the Ontology BuildingNadia Bebeshina-Clairet, Sylvie Despres and Mathieu Lafourcade . . . . . . . . . . . . . . . . . . . . . . . . . . . 92

Naive Regularizers for Low-Resource Neural Machine TranslationMeriem Beloucif, Ana Valeria Gonzalez, Marcel Bollmann and Anders Søgaard . . . . . . . . . . . . . 102

Exploring Graph-Algebraic CCG Combinators for Syntactic-Semantic AMR ParsingSebastian Beschke . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 112

Quasi Bidirectional Encoder Representations from Transformers for Word Sense DisambiguationMichele Bevilacqua and Roberto Navigli . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 122

Evaluating the Consistency of Word Embeddings from Small DataJelke Bloem, Antske Fokkens and Aurélie Herbelot . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 132

Cross-Domain Training for Goal-Oriented Conversational AgentsAlexandra Maria Bodîrlau, Stefania Budulan and Traian Rebedea . . . . . . . . . . . . . . . . . . . . . . . . . . 142

xi

Volume 1

Learning Sentence Embeddings for Coherence Modelling and BeyondTanner Bohn, Yining Hu, Jinhang Zhang and Charles Ling . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 151

Risk Factors Extraction from Clinical Texts Based on Linked Open DataSvetla Boytcheva, Galia Angelova and Zhivko Angelov . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 161

Parallel Sentence Retrieval From Comparable Corpora for Biomedical Text SimplificationRémi Cardon and Natalia Grabar . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 168

Classifying Author Intention for Writer Feedback in Related WorkArlene Casey, Bonnie Webber and Dorota Glowacka . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 178

Sparse Victory – A Large Scale Systematic Comparison of Count-Based and Prediction-Based Vectoriz-ers for Text Classification

Rupak Chakraborty, Ashima Elhence and Kapil Arora . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 188

A Fine-Grained Annotated Multi-Dialectal Arabic CorpusAnis Charfi, Wajdi Zaghouani, Syed Hassan Mehdi and Esraa Mohamed . . . . . . . . . . . . . . . . . . . . 198

Personality-Dependent Neural Text SummarizationPablo Costa and Ivandré Paraboni . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 205

Self-Adaptation for Unsupervised Domain AdaptationXia Cui and Danushka Bollegala . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 213

Speculation and Negation Detection in French Biomedical CorporaClément Dalloux, Vincent Claveau and Natalia Grabar . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 223

Porting Multilingual Morphological Resources to OntoLex-LemonThierry Declerck and Stefania Racioppa . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 233

Dependency-Based Self-Attention for Transformer NMTHiroyuki Deguchi, Akihiro Tamura and Takashi Ninomiya . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 239

Detecting Toxicity in News Articles: Application to BulgarianYoan Dinkov, Ivan Koychev and Preslav Nakov . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 247

De-Identification of Emails: Pseudonymizing Privacy-Sensitive Data in a German Email CorpusElisabeth Eder, Ulrike Krieg-Holz and Udo Hahn . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 259

Lexical Quantile-Based Text Complexity MeasureMaksim Eremeev and Konstantin Vorontsov . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 270

Demo Application for LETO: Learning Engine Through OntologiesSuilan Estevez-Velarde, Andrés Montoyo, Yudivian Almeida-Cruz, Yoan Gutiérrez, Alejandro Piad-

Morffis and Rafael Muñoz . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 276

Sentence Simplification for Semantic Role Labelling and Information ExtractionRichard Evans and Constantin Orasan . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 285

OlloBot - Towards A Text-Based Arabic Health Conversational Agent: Evaluation and ResultsAhmed Fadhil and Ahmed AbuRa’ed . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 295

Developing the Old Tibetan TreebankChristian Faggionato and Marieke Meelen . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 304

xii

Summarizing Legal Rulings: Comparative ExperimentsDiego Feijo and Viviane Moreira . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 313

Entropy as a Proxy for Gap Complexity in Open Cloze TestsMariano Felice and Paula Buttery . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 323

Song Lyrics Summarization Inspired by Audio ThumbnailingMichael Fell, Elena Cabrio, Fabien Gandon and Alain Giboin . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 328

Comparing Automated Methods to Detect Explicit Content in Song LyricsMichael Fell, Elena Cabrio, Michele Corazza and Fabien Gandon . . . . . . . . . . . . . . . . . . . . . . . . . . 338

Linguistic Classification: Dealing Jointly with Irrelevance and InconsistencyLaura Franzoi, Andrea Sgarro, Anca Dinu and Liviu P. Dinu . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 345

Corpus Lexicography in a Wider ContextChen Gafni . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 353

A Universal System for Automatic Text-to-Phonetics ConversionChen Gafni . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 360

Two Discourse Tree - Based Approaches to Indexing AnswersBoris Galitsky and Dmitry Ilvovsky . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 367

Discourse-Based Approach to Involvement of Background Knowledge for Question AnsweringBoris Galitsky and Dmitry Ilvovsky . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 373

On a Chatbot Providing Virtual DialoguesBoris Galitsky, Dmitry Ilvovsky and Elizaveta Goncharova . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 382

Assessing Socioeconomic Status of Twitter Users: A SurveyDhouha Ghazouani, Luigi Lancieri, Habib Ounelli and Chaker Jebari . . . . . . . . . . . . . . . . . . . . . . . 388

Divide and Extract – Disentangling Clause Splitting and Proposition ExtractionDarina Gold and Torsten Zesch . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 399

Sparse Coding in Authorship Attribution for Polish TweetsPiotr Grzybowski, Ewa Juralewicz and Maciej Piasecki . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 409

Automatic Question Answering for Medical MCQs: Can It Go Further than Information Retrieval?Le An Ha and Victoria Yaneva . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 418

Self-Knowledge Distillation in Natural Language ProcessingSangchul Hahn and Heeyoul Choi . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 423

From the Paft to the Fiiture: A Fully Automatic NMT and Word Embeddings Method for OCR Post-Correction

Mika Hämäläinen and Simon Hengchen . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 431

Investigating Terminology Translation in Statistical and Neural Machine Translation: A Case Study onEnglish-to-Hindi and Hindi-to-English

Rejwanul Haque, Md Hasanuzzaman and Andy Way . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 437

Beyond English-Only Reading Comprehension: Experiments in Zero-Shot Multilingual Transfer for Bul-garian

Momchil Hardalov, Ivan Koychev and Preslav Nakov . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 447

xiii

Tweaks and Tricks for Word Embedding DisruptionsAmir Hazem and Nicolas Hernandez . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 460

Meta-Embedding Sentence Representation for Textual SimilarityAmir Hazem and Nicolas Hernandez . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 465

Emoji Powered Capsule Network to Detect Type and Target of Offensive Posts in Social MediaHansi Hettiarachchi and Tharindu Ranasinghe . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 474

EoANN: Lexical Semantic Relation Classification Using an Ensemble of Artificial Neural NetworksRayehe Hosseini Pour and Mehrnoush Shamsfard . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 481

Opinions Summarization: Aspect Similarity Recognition Relaxes the Constraint of Predefined AspectsNguyen Huy Tien, Le Tung Thanh and Nguyen Minh Le . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 487

Discourse-Aware Hierarchical Attention Network for Extractive Single-Document SummarizationTatsuya Ishigaki, Hidetaka Kamigaito, Hiroya Takamura and Manabu Okumura . . . . . . . . . . . . . 497

Semi-Supervised Induction of POS-Tag Lexicons with Tree ModelsMaciej Janicki . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .507

Word Sense Disambiguation Based on Constrained Random Walks in Linked Semantic NetworksArkadiusz Janz and Maciej Piasecki . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 516

Classification of Micro-Texts Using Sub-Word EmbeddingsMihir Joshi and Nur Zincir-Heywood . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 526

Using Syntax to Resolve NPE in EnglishPayal Khullar, Allen Antony and Manish Shrivastava . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 534

Is Similarity Visually Grounded? Computational Model of Similarity for the Estonian LanguageClaudia Kittask and Eduard Barbu . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 541

Language-Agnostic Twitter-Bot DetectionJürgen Knauth . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 550

Multi-Level Analysis and Recognition of the Text Sentiment on the Example of Consumer OpinionsJan Kocon, Monika Zasko-Zielinska and Piotr Miłkowski . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 559

A Qualitative Evaluation Framework for Paraphrase IdentificationVenelin Kovatchev, M. Antònia Martí, Maria Salamo and Javier Beltran . . . . . . . . . . . . . . . . . . . . . 568

Study on Unsupervised Statistical Machine Translation for BacktranslationAnush Kumar, Nihal V. Nayak, Aditya Chandra and Mydhili K. Nair . . . . . . . . . . . . . . . . . . . . . . . 578

Towards Functionally Similar Corpus Resources for TranslationMaria Kunilovskaya and Serge Sharoff . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 583

Question Similarity in Community Question Answering: A Systematic Exploration of PreprocessingMethods and Models

Florian Kunneman, Thiago Castro Ferreira, Emiel Krahmer and Antal van den Bosch . . . . . . . . 593

A Classification-Based Approach to Cognate Detection Combining Orthographic and Semantic Similar-ity Information

Sofie Labat and Els Lefever . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 602

xiv

Resolving Pronouns for a Resource-Poor Language, Malayalam Using Resource-Rich Language, Tamil.Sobha Lalitha Devi . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 611

Semantic Role Labeling with Pretrained Language Models for Known and Unknown PredicatesDaniil Larionov, Artem Shelmanov, Elena Chistova and Ivan Smirnov . . . . . . . . . . . . . . . . . . . . . . 619

A Structural Approach to Enhancing WordNet with Conceptual Frame SemanticsSvetlozara Leseva and Ivelina Stoyanova . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 629

Compositional Hyponymy with Positive OperatorsMartha Lewis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 638

The Impact of Semantic Linguistic Features in Relation Extraction: A Logical Relational Learning Ap-proach

Rinaldo Lima, Bernard Espinasse and Frederico Freitas . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 648

Detecting Anorexia in Spanish TweetsPilar López Úbeda, Flor Miriam Plaza del Arco, Manuel Carlos Díaz Galiano, L. Alfonso Urena

Lopez and Maite Martin . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 655

A Type-Theoretical Reduction of Morphological, Syntactic and Semantic Compositionality to a SingleLevel of Description

Erkki Luuk . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 664

v-trel: Vocabulary Trainer for Tracing Word Relations - An Implicit Crowdsourcing ApproachVerena Lyding, Christos Rodosthenous, Federico Sangati, Umair ul Hassan, Lionel Nicolas, Alexan-

der König, Jolita Horbacauskiene and Anisia Katinskaia. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .674

Jointly Learning Author and Annotated Character N-gram Embeddings: A Case Study in Literary TextSuraj Maharjan, Deepthi Mave, Prasha Shrestha, Manuel Montes, Fabio A. González and Thamar

Solorio . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 684

Generating Challenge Datasets for Task-Oriented Conversational Agents through Self-PlaySourabh Majumdar, Serra Sinem Tekiroglu and Marco Guerini . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 693

Sentiment Polarity Detection in Azerbaijani Social News ArticlesSevda Mammadli, Shamsaddin Huseynov, Huseyn Alkaramov, Ulviyya Jafarli, Umid Suleymanov

and Samir Rustamov. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .703

Inforex — a Collaborative System for Text Corpora Annotation and Analysis Goes OpenMichał Marcinczuk and Marcin Oleksy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 711

Semantic Language Model for Tunisian DialectAbir Masmoudi, Rim Laatar, Mariem Ellouze and Lamia Hadrich Belguith . . . . . . . . . . . . . . . . . . 720

Automatic Diacritization of Tunisian Dialect Text Using Recurrent Neural NetworkAbir Masmoudi, Mariem Ellouze and Lamia Hadrich Belguith . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 730

Comparing MT Approaches for Text NormalizationClaudia Matos Veliz, Orphee De Clercq and Veronique Hoste . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 740

Sentiment and Emotion Based Representations for Fake Reviews DetectionAlimuddin Melleng, Anna Jurek-Loughrey and Deepak P. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 750

xv

Volume 2

NLP Community Perspectives on ReplicabilityMargot Mieskes, Karën Fort, Aurélie Névéol, Cyril Grouin and Kevin Cohen . . . . . . . . . . . . . . . . 768

Unsupervised Data Augmentation for Less-Resourced Languages with no Standardized SpellingAlice Millour and Karën Fort . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 776

Neural Feature Extraction for Contextual Emotion DetectionElham Mohammadi, Hessam Amini and Leila Kosseim. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .785

Empirical Study of Diachronic Word Embeddings for Scarce DataSyrielle Montariol and Alexandre Allauzen. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .795

A Fast and Accurate Partially Deterministic Morphological AnalysisHajime Morita and Tomoya Iwakura . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 804

incom.py - A Toolbox for Calculating Linguistic Distances and Asymmetries between Related LanguagesMarius Mosbach, Irina Stenger, Tania Avgustinova and Dietrich Klakow . . . . . . . . . . . . . . . . . . . . 810

A Holistic Natural Language Generation Framework for the Semantic WebAxel-Cyrille Ngonga Ngomo, Diego Moussallem and Lorenz Bühmann . . . . . . . . . . . . . . . . . . . . . 819

Building a Comprehensive Romanian Knowledge Base for Drug AdministrationBogdan Nicula, Mihai Dascalu, Maria-Dorinela Sîrbu, S, tefan Traus, an-Matu andAlexandru Nut, a . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 829

Summary Refinement through DenoisingNikola Nikolov, Alessandro Calmanovici and Richard Hahnloser . . . . . . . . . . . . . . . . . . . . . . . . . . . 837

Large-Scale Hierarchical Alignment for Data-Driven Text RewritingNikola Nikolov and Richard Hahnloser . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 844

Dependency-Based Relative Positional Encoding for Transformer NMTYutaro Omote, Akihiro Tamura and Takashi Ninomiya . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 854

From Image to Text in Sentiment Analysis via Regression and Deep LearningDaniela Onita, Liviu P. Dinu and Adriana Birlutiu . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .862

Building a Morphological Analyser for LazEsra Önal and Francis Tyers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 869

Term Based Semantic Clusters for Very Short Text ClassificationJasper Paalman, Shantanu Mullick, Kalliopi Zervanou, Yingqian Zhang . . . . . . . . . . . . . . . . . . . . . 878

Quotation Detection and Classification with a Corpus-Agnostic ModelSean Papay and Sebastian Padó . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 888

Validation of Facts Against Textual SourcesVamsi Krishna Pendyala, Simran Sinha, Satya Prakash, Shriya Reddy and Anupam Jamatia . . . 895

A Neural Network Component for Knowledge-Based Semantic Representations of TextAlejandro Piad-Morffis, Rafael Muñoz, Yudivian Almeida-Cruz, Yoan Gutiérrez, Suilan Estevez-

Velarde and Andrés Montoyo . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 904

xvi

Turning Silver into Gold: Error-Focused Corpus Reannotation with Active LearningPierre André Ménard and Antoine Mougeot . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 758

Combining SMT and NMT Back-Translated Data for Efficient NMTAlberto Poncelas, Maja Popovic, Dimitar Shterionov, Gideon Maillette de Buy Wenniger and Andy

Way . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 922

Unsupervised Dialogue Intent Detection via Hierarchical Topic ModelArtem Popov, Victor Bulatov, Darya Polyudova and Eugenia Veselova . . . . . . . . . . . . . . . . . . . . . . 932

Graph Embeddings for Frame IdentificationAlexander Popov and Jennifer Sikos . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 939

Know Your Graph. State-of-the-Art Knowledge-Based WSDAlexander Popov, Kiril Simov and Petya Osenova . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 949

Are Ambiguous Conjunctions Problematic for Machine Translation?Maja Popovic and Sheila Castilho . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 959

ULSAna: Universal Language Semantic AnalyzerOndrej Pražák and Miloslav Konopík . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 967

Machine Learning Approach to Fact-Checking in West Slavic LanguagesPavel Pribán, Tomáš Hercig and Josef Steinberger . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 973

NE-Table: A Neural Key-Value Table for Named EntitiesJanarthanan Rajendran, Jatin Ganhotra, Xiaoxiao Guo, Mo Yu, Satinder Singh and Lazaros Poly-

menakos. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .980

Enhancing Unsupervised Sentence Similarity Methods with Deep Contextualised Word RepresentationsTharindu Ranasinghe, Constantin Orasan and Ruslan Mitkov . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 994

Semantic Textual Similarity with Siamese Neural NetworksTharindu Ranasinghe, Constantin Orasan and Ruslan Mitkov . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1004

Analysing the Impact of Supervised Machine Learning on Automatic Term Extraction: HAMLET vsTermoStat

Ayla Rigouts Terryn, Patrick Drouin, Veronique Hoste and Els Lefever . . . . . . . . . . . . . . . . . . . . .1012

Distant Supervision for Sentiment Attitude ExtractionNicolay Rusnachenko, Natalia Loukachevitch and Elena Tutubalina . . . . . . . . . . . . . . . . . . . . . . . 1022

Self-Attentional Models Application in Task-Oriented Dialogue Generation SystemsMansour Saffar Mehrjardi, Amine Trabelsi and Osmar R. Zaiane . . . . . . . . . . . . . . . . . . . . . . . . . . 1031

Whom to Learn From? Graph- vs. Text-Based Word EmbeddingsMałgorzata Salawa, António Branco, Ruben Branco, João António Rodrigues

and Chakaveh Saedi . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1041

Persistence Pays Off: Paying Attention to What the LSTM Gating Mechanism PersistsGiancarlo Salton and John Kelleher . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1052

Development and Evaluation of Three Named Entity Recognition Systems for Serbian - The Case ofPersonal Names

Branislava Šandrih, Cvetana Krstev and Ranka Stankovic . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .1060

xvii

Toponym Detection in the Bio-Medical Domain: A Hybrid Approach with Deep LearningAlistair Plum, Tharindu Ranasinghe and Constantin Orasan . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 912

The "Jump and Stay" Method to Discover Proper Verb Centered Constructions in Corpus LatticesBálint Sass . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .1076

Offence in Dialogues: A Corpus-Based StudyJohannes Schäfer and Ben Burtenshaw . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1085

EmoTag – Towards an Emotion-Based Analysis of EmojisAbu Awal Md Shoeb, Shahab Raji and Gerard de Melo . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1094

A Morpho-Syntactically Informed LSTM-CRF Model for Named Entity RecognitionLilia Simeonova, Kiril Simov, Petya Osenova and Preslav Nakov . . . . . . . . . . . . . . . . . . . . . . . . . . 1104

Named Entity Recognition in Information Security Domain for RussianAnastasiia Sirotina and Natalia Loukachevitch. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .1114

Cross-Family Similarity Learning for Cognate Identification in Low-Resource LanguagesEliel Soisalon-Soininen and Mark Granroth-Wilding . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1121

Automatic Detection of Translation DirectionIlia Sominsky and Shuly Wintner . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1131

Automated Text Simplification as a Preprocessing Step for Machine Translation into an Under-ResourcedLanguage

Sanja Štajner and Maja Popovic . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1141

Investigating Multilingual Abusive Language Detection: A Cautionary TaleKenneth Steimel, Daniel Dakota, Yue Chen and Sandra Kübler . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1151

Augmenting a BiLSTM Tagger with a Morphological Lexicon and a Lexical Category Identification StepSteinþór Steingrímsson, Örvar Kárason and Hrafn Loftsson . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1161

Comparison of Machine Learning Approaches for Industry Classification Based on Textual Descriptionsof Companies

Andrey Tagarev, Nikola Tulechki and Svetla Boytcheva . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1169

A Quantum-Like Approach to Word Sense DisambiguationFabio Tamburini . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1176

Understanding Neural Machine Translation by Simplification: The Case of Encoder-Free ModelsGongbo Tang, Rico Sennrich and Joakim Nivre . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1186

Text-Based Joint Prediction of Numeric and Categorical Attributes of Entities in Knowledge BasesV Thejas, Abhijeet Gupta and Sebastian Padó . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1194

SenZi: A Sentiment Analysis Lexicon for the Latinised Arabic (Arabizi)Taha Tobaili, Miriam Fernandez, Harith Alani, Sanaa Sharafeddine, Hazem Hajj

and Goran Glavaš . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1203

Mining the UK Web Archive for Semantic Change DetectionAdam Tsakalidis, Marya Bazzi, Mihai Cucuringu, Pierpaolo Basile and Barbara McGillivray 1212

Cross-Lingual Word Embeddings for Morphologically Rich LanguagesAhmet Üstün, Gosse Bouma and Gertjan van Noord . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1222

xviii

Moral Stance Recognition and Polarity Classification from Twitter and Elicited TextWesley Santos and Ivandré Paraboni . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1069

Deep Learning Contextual Models for Prediction of Sport Events Outcome from Sportsmen InterviewsBoris Velichkov, Ivan Koychev and Svetla Boytcheva . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1240

Exploiting Frame-Semantics and Frame-Semantic Parsing for Automatic Extraction of Typological In-formation from Descriptive Grammars of Natural Languages

Shafqat Mumtaz Virk, Azam Sheikh Muhammad, Lars Borin, Muhammad Irfan Aslam, SaaniaIqbal and Nazia Khurram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1247

Exploiting Open IE for Deriving Multiple Premises Entailment CorpusMartin Víta and Jakub Klímek . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1257

Towards Adaptive Text Summarization: How Does Compression Rate Affect Summary Readability of L2Texts?

Tatiana Vodolazova and Elena Lloret . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1265

The Impact of Rule-Based Text Generation on the Quality of Abstractive SummariesTatiana Vodolazova and Elena Lloret . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1275

ETNLP: A Visual-Aided Systematic Approach to Select Pre-Trained Embeddings for a Downstream TaskSon Vu Xuan, Thanh Vu, Son Tran and Lili Jiang . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1285

Tagger for Polish Computer Mediated Communication TextsWiktor Walentynowicz, Maciej Piasecki and Marcin Oleksy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1295

Evaluation of Vector Embedding Models in Clustering of Text DocumentsTomasz Walkowiak and Mateusz Gniewkowski . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1304

Bigger versus Similar: Selecting a Background Corpus for First Story Detection Based on DistributionalSimilarity

Fei Wang, Robert J. Ross and John D. Kelleher . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1312

Predicting Sentiment of Polish Language Short TextsAleksander Wawer and Julita Sobiczewska . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1321

Improving Named Entity Linking Corpora QualityAlbert Weichselbraun, Adrian M.P. Brasoveanu, Philipp Kuntschik and Lyndon J.B. Nixon . . 1328

Sequential Graph Dependency ParserSean Welleck and Kyunghyun Cho . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1338

Term-Based Extraction of Medical Information: Pre-Operative Patient Education Use CaseMartin Wolf, Volha Petukhova and Dietrich Klakow . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1346

A Survey of the Perceived Text Adaptation Needs of Adults with AutismVictoria Yaneva, Constantin Orasan, Le An Ha and Natalia Ponomareva . . . . . . . . . . . . . . . . . . . 1356

An Open, Extendible, and Fast Turkish Morphological AnalyzerOlcay Taner Yıldız, Begüm Avar and Gökhan Ercan . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1364

Self-Attention Networks for Intent DetectionSevinj Yolchuyeva, Géza Németh and Bálint Gyires-Tóth . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1373

Turkish Tweet Classification with Transformer EncoderAtıf Emre Yüksel, Yasar Alim Türkmen, Arzucan Özgür and Berna Altınel . . . . . . . . . . . . . . . . 1380

xix

It Takes Nine to Smell a Rat: Neural Multi-Task Learning for Check-Worthiness PredictionSlavena Vasileva, Pepa Atanasova, Lluís Màrquez, Alberto Barrón-Cedeño and Preslav Nakov1229

Multilingual Dynamic Topic ModelElaine Zosa and Mark Granroth-Wilding . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1388

A Wide-Coverage Context-Free Grammar for Icelandic and an Accompanying Parsing SystemVilhjálmur Þorsteinsson, Hulda Óladóttir and Hrafn Loftsson . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1397

xx